Configure embedder model

Witty needs a valid embedder model. This section will describe how to add a embedder configuration.

Embedder structure

An embedder model is composed of these fields:

• provider: embedder provider;
• api_key: api key of the provider;
• endpoint: URL where the embedder model is located;
• api_version: api version defined by the provider;
• model: embedder model name;
• deployment: deployment name. It could be different from model.

Here's an example of a embedder configuration:

{
    "provider": "azure_openai",
    "api_key": "xxx",
    "endpoint": "https://xxx.cognitiveservices.azure.com/",
    "api_version": "2025-01-01-preview",
    "model": "text-embedding-3-large",
    "deployment": "text-embedding-3-large-witty"
}

Interacting with embedder

Currently, there are the following APIs to interact with embedder configuration:

• GET /witty/v1/embedder/config: retrieve the embedder configuration;
• POST /witty/v1/embedder/config: create/edit a embedder configuration. The body is a JSON in the embedder structure seen before.

Supported models

Currently Witty microservice has been tested against the following models/providers:

Embedder Provider	Model
azure_openai	text-embedding-3-large
azure_openai	text-embedding-3-small